Cleanifier: contamination removal from microbial sequences using spaced seeds of a human pangenome index.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41252442", "kind": "science-record", "revision": 1, "content_hash": "sha256:375da1c61aa5ac3e4e5f5c5722852c0cf4f97670543b4ecd2d8c6f94ea436f77", "created_at": "2026-11-01T20:31:17Z", "updated_at": "2026-11-01T20:31:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Cleanifier: contamination removal from microbial sequences using spaced seeds of a human pangenome index.", "doi": "10.1093/bioinformatics/btaf632", "pmid": "41252442", "authors": ["Jens Zentgraf", "Johanna Elena Schmitz", "Sven Rahmann"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "MOTIVATION: The first step when working with DNA data of human-derived microbiomes is to remove human contamination for two reasons. First, many countries have strict privacy and data protection guidelines for human sequence data, so microbiome data containing partly human data cannot be easily further processed or published. Second, human contamination may cause problems in downstream analysis, such as metagenomic binning or genome assembly. For large-scale metagenomics projects, fast and accurate removal of human contamination is therefore critical.\nRESULTS: We introduce Cleanifier, a fast and memory frugal alignment-free tool for detecting and removing human contamination based on gapped k-mers, or spaced seeds. Cleanifier uses a pangenome index of known human gapped k-mers, and the creation and use of alternative references is also possible. Reads are classified and filtered according to their gapped k-mer content. Cleanifier supports two filtering modes: one that queries all gapped k-mers and one that queries only a sample of them. A comparison of Cleanifier with other state-of-the-art tools shows that the sampling mode makes Cleanifier the fastest method with comparable accuracy. When using a probabilistic Cuckoo filter to store the complete k-mer set, Cleanifier has similar memory requirements to methods that use a sampled minimizer index. At the same time, Cleanifier is more flexible, because it can use different sampling methods on the same index.\nAVAILABILITY AND IMPLEMENTATION: Cleanifier is available via gitlab (https://gitlab.com/rahmannlab/cleanifier), PyPi (https://pypi.org/project/cleanifier/), and Bioconda (https://anaconda.org/bioconda/cleanifier). The pre-computed human pangenome index is available at Zenodo (https://doi.org/10.5281/zenodo.15639519).", "claims": [{"id": "claim-data-access", "statement": "All data used in the evaluation is available online (Zook et al. 2016, Meyer et al. 2025). Dataset URLs are provided in the Supplement, available as supplementary data at Bioinformatics online. The pre-built Cleanifier index is available at Zenodo (https://doi.org/10.5281/zenodo.15639519) or can be downloaded using the cleanifier download command.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41252442", "locator": "sections[32] \"Data availability\" paragraph 2", "quote": "All data used in the evaluation is available online (Zook et al. 2016, Meyer et al. 2025). Dataset URLs are provided in the Supplement, available as supplementary data at Bioinformatics online. The pre-built Cleanifier index is available at Zenodo (https://doi.org/10.5281/zenodo.15639519) or can be downloaded using the cleanifier download command."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A comparison of Cleanifier with other state-of-the-art tools shows that the sampling mode makes Cleanifier the fastest method with comparable accuracy.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41252442", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "A comparison of Cleanifier with other state-of-the-art tools shows that the sampling mode makes Cleanifier the fastest method with comparable accuracy."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "A comparison of Cleanifier with other state-of-the-art tools shows that the sampling mode makes Cleanifier the fastest method with comparable accuracy.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41252442"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41252442", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf632", "sha256": "sha256:5a6ccfbb06d60526fe999e71cc471086534f8eaa072b57c18a7bb2f35aee4df1", "bytes": 44275, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf632", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12758600", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["All data used in the evaluation is available online (Zook et al. 2016, Meyer et al. 2025). Dataset URLs are provided in the Supplement, available as supplementary data at Bioinformatics online. The pre-built Cleanifier index is available at Zenodo (https://doi.org/10.5281/zenodo.15639519) or can be downloaded using the cleanifier download command."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41252442"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:06:04Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13205, "completion_tokens": 2793, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41252442", "type": "paper", "label": "pmid:41252442"}, {"id": "source:pmid:41252442", "type": "manuscript", "label": "PMID 41252442 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41252442", "type": "paper", "label": "pmid:41252442"}, {"id": "source:pmid:41252442", "type": "manuscript", "label": "PMID 41252442 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41252442", "type": "extraction", "used": ["source:pmid:41252442"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}